Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7872
    Prev
    Next
    INDEX
    Explanations

    Windows API function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ذة
    -0.80
    กรม
    -0.79
     ав
    -0.73
     كلام
    -0.73
    hånd
    -0.71
    กล้
    -0.71
     résine
    -0.71
    潍
    -0.69
     裙
    -0.69
    isle
    -0.68
    POSITIVE LOGITS
    A
    1.05
     A
    1.00
    W
    0.75
    letta
    0.71
    brata
    0.68
     leta
    0.67
     Paine
    0.66
     bestellen
    0.66
    bull
    0.66
    zień
    0.65
    Activations Density 0.052%

    No Known Activations